⌦abliteratedmodels.org

Ornith-1.5-35B-Uncensored-YMQ

Ornith-1.5-35B-Uncensored-YMQ is a abliterated and uncensored variant of 0xKitkat/Ornith-1.5-35B-A3B-Uncensored, published on Hugging Face by zerodigest. It is 35B parameters, 48GB VRAM class class and apache-2.0 licence. It is distributed across 2 repositories in GGUF format, totalling 25.2K downloads.

Abliteration + uncensored fine-tune35BOrnith25B – 50B↓ 25,216♥ 3
View on Hugging Face ↗Base model ↗

Specification

Model name
Ornith-1.5-35B-Uncensored-YMQ
Source repository
zerodigest/Ornith-1.5-35B-Uncensored-YMQ-MTP-GGUF
Base model
0xKitkat/Ornith-1.5-35B-A3B-Uncensored
Publisher
zerodigest
Parameters
35B
Hardware class
25B – 50B — 48GB VRAM class
Licence
apache-2.0
Task
Text generation
Context window
Not documented
Ablation scope
Not stated by the publisher
Formats available
GGUF
First indexed
21 Aug 2026
Last updated
4 Sept 2026

Ablation technique

How Ornith-1.5-35B-Uncensored-YMQ was modified, and what that implies.

Abliteration + uncensored fine-tune

Directional ablation combined with additional fine-tuning on unfiltered data, so behaviour diverges from the base model beyond refusal removal alone.

Reported scope: Not stated by the publisher. Publishers frequently omit this, so verify behaviour empirically rather than assuming full coverage.

From the publisher’s model card

“Every single ZeroDigest YMQ-MTP release is handcrafted and manually calibrated via intensive importance-matrix sweeps to protect critical logic pathways. This project is entirely independent research—no automation bots, no corporate backers, and no external funding. Running multi-hour compute arrays consumes massive...”

Running it

Commands are templates — confirm the exact repository and quant file before use.

llama.cpp / GGUF
hf download zerodigest/Ornith-1.5-35B-Uncensored-YMQ-MTP-GGUF --local-dir ./ornith-1.5-35b-uncensored-ymq
llama-cli -m ./ornith-1.5-35b-uncensored-ymq/<file>.gguf -p "..."
Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "zerodigest/Ornith-1.5-35B-Uncensored-YMQ-MTP-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
    repo, torch_dtype="auto", device_map="auto"
)
vLLM
vllm serve zerodigest/Ornith-1.5-35B-Uncensored-YMQ-MTP-GGUF --trust-remote-code

Downloads and variants (1)

The only published repository of Ornith-1.5-35B-Uncensored-YMQ.

RepositoryFormatDownloads
zerodigest/Ornith-1.5-35B-Uncensored-YMQ-MTP-GGUFsourceGGUF25.2K

Security-team assessment

Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.

  • Ornith-1.5-35B-Uncensored-YMQ will attempt offensive-security prompts that a hosted commercial model declines, which is what makes it usable for red-team corpus generation and for measuring what an unaligned model of this class produces.
  • Capability is inherited from 0xKitkat/Ornith-1.5-35B-A3B-Uncensored, not added by ablation — at 35B parameters, expect roughly the base model’s competence, minus some instruction-following fidelity.
  • The publisher does not state which layers were ablated, so assume nothing about refusal consistency — probe it directly.
  • This release adds fine-tuning on unfiltered data, so its behaviour diverges from the base model beyond refusal removal — differences you measure cannot be attributed to ablation alone.
  • Declared licence is apache-2.0, but the terms that bind you are 0xKitkat/Ornith-1.5-35B-A3B-Uncensored’s — a re-release cannot grant more than its parent.

Handling: run it isolated, put moderation in front of it if anyone outside your team can reach it, and verify the weights before loading — these are third-party artifacts. Full handling and licence guidance.

Metadata for Ornith-1.5-35B-Uncensored-YMQ is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with zerodigest, and does not independently verify publisher claims. See responsible use.